Describe the problem you are having
I currently have proxmox running on a small mini pc with an Intel N100 cpu. (For completeness sake I've set up SR-IOV stuff to basically split the GPU into 7 to be used by VM's and LXC containers).
When I enable hwacceleration I can see usage on my GPU by calling intel_gpu_top -d sriov:
ffmpeg:
hwaccel_args: preset-vaapi
When I comment this section out and add the stuff for openvino I don't see any GPU usage at all:
detectors:
ov:
type: openvino
device: GPU
model:
path: /openvino-model/ssdlite_mobilenet_v2.xml
model:
width: 300
height: 300
input_tensor: nhwc
input_pixel_format: bgr
labelmap_path: /openvino-model/coco_91cl_bkgr.txt
I'm having the feeling that my GPU is not being used for inference, but then again, I have no idea how to check this and be 100% certain.
Version
0.12.1-367d724
Frigate config file
# ffmpeg:
# hwaccel_args: preset-vaapi
detectors:
ov:
type: openvino
device: GPU
model:
path: /openvino-model/ssdlite_mobilenet_v2.xml
model:
width: 300
height: 300
input_tensor: nhwc
input_pixel_format: bgr
labelmap_path: /openvino-model/coco_91cl_bkgr.txt
cameras:
G3Instant2:
ffmpeg:
inputs:
- path: rtsps://***************
roles:
- detect
detect:
width: 1920
height: 1080
objects:
track:
- person
- dog
- cat
- car
- motorcycle
- bird
- bicycle
snapshots:
enabled: True
record:
enabled: True
events:
retain:
default: 5
### docker-compose file or Docker CLI command
```yaml
version: '3'
services:
frigate:
container_name: frigate
privileged: true # this may not be necessary for all setups
restart: unless-stopped
image: ghcr.io/blakeblackshear/frigate:stable
shm_size: "640mb" # update for your cameras based on calculation above
devices:
#- /dev/bus/usb:/dev/bus/usb # passes the USB Coral, needs to be modified for other versions
#- /dev/apex_0:/dev/apex_0 # passes a PCIe Coral, follow driver instructions here https://coral.ai/docs/m2/get-started/#2a-on-linux
- /dev/dri/renderD131:/dev/dri/renderD128 # for intel hwaccel, needs to be updated for your hardware
volumes:
- /etc/localtime:/etc/localtime:ro
- /root/dockercomposers/frigate/config/config.yml:/config/config.yml
- /root/dockercomposers/frigate/storage:/media/frigate
- type: tmpfs # Optional: 1GB of memory, reduces SSD/SD Card wear
target: /tmp/cache
tmpfs:
size: 1000000000
ports:
- "5000:5000"
- "8554:8554" # RTSP feeds
- "8555:8555/tcp" # WebRTC over tcp
- "8555:8555/udp" # WebRTC over udp
environment:
FRIGATE_RTSP_PASSWORD: ************
#LIBVA_DRIVER_NAME: "i965"
cap_add:
- PERFMON
Relevant log output
frigate | s6-rc: info: service s6rc-fdholder: starting
frigate | s6-rc: info: service s6rc-oneshot-runner: starting
frigate | s6-rc: info: service s6rc-fdholder successfully started
frigate | s6-rc: info: service s6rc-oneshot-runner successfully started
frigate | s6-rc: info: service fix-attrs: starting
frigate | s6-rc: info: service fix-attrs successfully started
frigate | s6-rc: info: service legacy-cont-init: starting
frigate | s6-rc: info: service legacy-cont-init successfully started
frigate | s6-rc: info: service log-prepare: starting
frigate | s6-rc: info: service log-prepare successfully started
frigate | s6-rc: info: service nginx-log: starting
frigate | s6-rc: info: service go2rtc-log: starting
frigate | s6-rc: info: service frigate-log: starting
frigate | s6-rc: info: service nginx-log successfully started
frigate | s6-rc: info: service go2rtc-log successfully started
frigate | s6-rc: info: service go2rtc: starting
frigate | 2024-01-10 22:36:45.479210387 [INFO] Preparing go2rtc config...
frigate | s6-rc: info: service frigate-log successfully started
frigate | s6-rc: info: service go2rtc successfully started
frigate | s6-rc: info: service go2rtc-healthcheck: starting
frigate | s6-rc: info: service frigate: starting
frigate | 2024-01-10 22:36:45.496095407 [INFO] Starting Frigate...
frigate | s6-rc: info: service go2rtc-healthcheck successfully started
frigate | s6-rc: info: service frigate successfully started
frigate | s6-rc: info: service nginx: starting
frigate | 2024-01-10 22:36:45.533761952 [INFO] Starting NGINX...
frigate | s6-rc: info: service nginx successfully started
frigate | s6-rc: info: service legacy-services: starting
frigate | s6-rc: info: service legacy-services successfully started
frigate | 2024-01-10 22:36:45.716520261 [INFO] Starting go2rtc...
frigate | 2024-01-10 22:36:45.831381497 22:36:45.831 INF go2rtc version 1.2.0 linux/amd64
frigate | 2024-01-10 22:36:45.833704514 22:36:45.833 INF [api] listen addr=:1984
frigate | 2024-01-10 22:36:45.834463153 22:36:45.834 INF [rtsp] listen addr=:8554
frigate | 2024-01-10 22:36:45.835231722 22:36:45.835 INF [srtp] listen addr=:8443
frigate | 2024-01-10 22:36:45.835669794 22:36:45.835 INF [webrtc] listen addr=:8555
frigate | 2024-01-10 22:36:46.594316099 [2024-01-10 22:36:46] frigate.app INFO : Starting Frigate (0.12.1-367d724)
frigate | 2024-01-10 22:36:46.617808250 [2024-01-10 22:36:46] frigate.config WARNING : Customizing more than a detector model path is unsupported.
frigate | 2024-01-10 22:36:46.623013477 [2024-01-10 22:36:46] peewee_migrate INFO : Starting migrations
frigate | 2024-01-10 22:36:46.627016147 [2024-01-10 22:36:46] peewee_migrate INFO : There is nothing to migrate
frigate | 2024-01-10 22:36:46.642091207 [2024-01-10 22:36:46] detector.ov INFO : Starting detection process: 301
frigate | 2024-01-10 22:36:46.646803262 [2024-01-10 22:36:46] frigate.app INFO : Output process started: 303
frigate | 2024-01-10 22:36:46.651684731 [2024-01-10 22:36:46] frigate.app INFO : Camera processor started for G3Instant2: 306
frigate | 2024-01-10 22:36:46.656312105 [2024-01-10 22:36:46] frigate.app INFO : Camera processor started for G3Instant3: 308
frigate | 2024-01-10 22:36:46.660150303 [2024-01-10 22:36:46] frigate.app INFO : Camera processor started for G3Instant4: 309
frigate | 2024-01-10 22:36:46.664496321 [2024-01-10 22:36:46] frigate.app INFO : Capture process started for G3Instant2: 311
frigate | 2024-01-10 22:36:46.669141734 [2024-01-10 22:36:46] frigate.app INFO : Capture process started for G3Instant3: 313
frigate | 2024-01-10 22:36:46.673562457 [2024-01-10 22:36:46] frigate.app INFO : Capture process started for G3Instant4: 314
frigate | 2024-01-10 22:36:54.730492647 [2024-01-10 22:36:54] frigate.detectors.plugins.openvino INFO : Model Input Shape: {1, 300, 300, 3}
frigate | 2024-01-10 22:36:54.730496890 [2024-01-10 22:36:54] frigate.detectors.plugins.openvino INFO : Model Output-0 Shape: {1, 1, 100, 7}
frigate | 2024-01-10 22:36:54.730501064 [2024-01-10 22:36:54] frigate.detectors.plugins.openvino INFO : Model has 1 Output TensorsOperating system
Proxmox
Install method
Docker Compose
Coral version
CPU (no coral)
Any other information that may be helpful
No response
Describe the problem you are having
I currently have proxmox running on a small mini pc with an Intel N100 cpu. (For completeness sake I've set up SR-IOV stuff to basically split the GPU into 7 to be used by VM's and LXC containers).
When I enable hwacceleration I can see usage on my GPU by calling
intel_gpu_top -d sriov:When I comment this section out and add the stuff for openvino I don't see any GPU usage at all:
I'm having the feeling that my GPU is not being used for inference, but then again, I have no idea how to check this and be 100% certain.
Version
0.12.1-367d724
Frigate config file
Relevant log output
Operating system
Proxmox
Install method
Docker Compose
Coral version
CPU (no coral)
Any other information that may be helpful
No response